I want to use a learning program using keras in Google Collaboration.

I was going to use the program that I'm using as a spider in Google Collaboration, but I got an error.

import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.layers.current import LSTM
from tensorflow.keras.optimizers import Adam
from sklearn.model_selection import train_test_split
data = [ ]
data1 = [ ]
data2 = [ ]
target = [ ]
kairi=[ ]
jousyou=[]
maxlen = 60
day1 = [ ]
day2 = [ ]
day3 = [ ]
owarine=[ ]
・
・
・
・
・

'''
model setting
'''
n_in=len(X[0][0])  
n_hidden = 100
n_out=len(Y[0])  
def weight_variable (shape, name=None):
return np.random.normal(scale=.01, size=shape)
model=Sequential()
model.add(LSTM(n_hidden,
                    kernel_initializer = "random_uniform",
                    input_shape=(maxlen,n_in)))
model.add(Dense(n_hidden, kernel_initializer="random_uniform"))
model.add (Activation('sigmoid')
model.add(Dense(n_out, kernel_initializer="random_uniform"))
model.add (Activation('sigmoid')
optimizer=Adam (lr=0.001, beta_1=0.9, beta_2=0.999)
model.compile(loss='mean_squared_error',
              optimizer= optimizer)


'''
model learning
'''
epochs=500
batch_size=1000
model.fit(X_train,Y_train,
          batch_size = batch_size,
          epochs = epochs,
          validation_split = 0.25)

'''
That's it for learning.
'''

It looks like the model.fit part of this.
The error message is as follows:

UnimplementedError Traceback (most recent call last)
in()
173batch_size=batch_size,
174 epochs=epochs,
-->175 validation_split=0.25)

Thank you for your cooperation.

python tensorflow keras google-colaboratory

2022-09-30 13:58

1 Answers

When I tried below, I was able to run it with Google colab (runtime type: GPU, Python version 3.6.9, Keras version 2.4.3).
I left the sizes X and Y below appropriately, but is it correct?If it's correct, it worked in my environment, so I thought it might be due to the development environment.

''
model setting
'''

'''
※ Add the following two lines for operation verification
'''
X = np.random.random ([700, 60, 200])
Y = np.random.random ([700,100])

n_in=len(X[0][0])  
n_hidden = 100
n_out=len(Y[0])  
def weight_variable (shape, name=None):
  return np.random.normal(scale=.01, size=shape)

model=Sequential()
model.add(LSTM(n_hidden,
                    kernel_initializer = "random_uniform",
                    input_shape=(maxlen,n_in)))
model.add(Dense(n_hidden, kernel_initializer="random_uniform"))
model.add (Activation('sigmoid')
model.add(Dense(n_out, kernel_initializer="random_uniform"))
model.add (Activation('sigmoid')
optimizer=Adam (lr=0.001, beta_1=0.9, beta_2=0.999)
model.compile(loss='mean_squared_error',
              optimizer= optimizer)

'''
※ Add the following two lines for operation verification
'''
X_train=np.random.random([700,60,200])
Y_train=np.random.random([700,100])

'''
model learning
'''
epochs=500
batch_size=1000
model.fit(X_train,Y_train,
          batch_size = batch_size,
          epochs = epochs,
          validation_split = 0.25)

2022-09-30 13:58

If you have any answers or tips

Popular Tags

python x 4647

android x 1593

java x 1494

javascript x 1427

c x 927

c++ x 878

ruby-on-rails x 696

php x 692

python3 x 685

html x 656